Optimal Fusion Weights Form Intervals, Not Points: A Latency-Aware Study of Query-Adaptive WRRF
Under review.
Abstract
We build ten query-adaptive weighted reciprocal rank fusion (WRRF) methods for production search, showing they outperform standard RRF. We find that optimal fusion weights form intervals rather than single points, helping explain why RRF remains near-optimal for 10--38% of queries. We introduce an oracle/headroom-recovery framework with latency-aware tiering to make these gains practical in production, and evaluate across four sparse and dense retriever configurations (BM25/RM3, MiniLM, Qwen3).
Cite
@unpublished{MaWRRF2026,
title = {Optimal Fusion Weights Form Intervals, Not Points: A Latency-Aware Study of Query-Adaptive WRRF},
author = {Ma, Iris and Shekarchi, Zahra and Mcilroy, Stuart and Farrokh, Mahtab and Zarrinkalam, Fattane and Stremmel, Joel},
note = {Under review},
year = {2026}
}